natural language processing
PulseAugur coverage of natural language processing — every cluster mentioning natural language processing across labs, papers, and developer communities, ranked by signal.
9 天有情绪数据
-
New dataset annotates social perception dimensions of warmth and competence in text
Researchers have introduced W&C-Sent, a new dataset designed to annotate warmth and competence at the sentence level. This dataset contains over 1,600 English sentence-target pairs derived from social media posts. The a…
-
Sinhala NLP research hub releases transliteration systems and data resources
A new paper introduces the Swa-bhasha Resource Hub, a collection of data and algorithms for Romanized Sinhala to Sinhala transliteration developed between 2020 and 2025. These resources are crucial for advancing Sinhala…
-
LLM在教育、事实核查和患病率估计中表现出偏见
研究人员开发了新的计算指标来评估教育NLP系统的教学一致性，结果显示学生通常使用这些工具进行答案提取而非持续学习。另一篇论文认为，逻辑健全性是使用LLM进行神经符号事实核查的不可靠标准，因为人类推理可能偏离严格的逻辑结论。第三项研究引入了多重校准作为一种使用LLM进行无偏患病率估计的方法，特别是在协变量偏移下，而标准校准方法无法解决这个问题。
-
Eugene Yan shares strategies for continuous machine learning education
Eugene Yan's essay offers practical advice for staying current in the rapidly evolving field of machine learning. He suggests actively experimenting with new tools and techniques in projects, sharing learnings with coll…
-
研究比较BERT和T5在NER上的表现；文章推崇论文阅读对数据科学家的益处
一篇新的arXiv论文详细介绍了一项研究，该研究比较了BERT和T5模型在命名实体识别（NER）上的表现，分析了它们在不同标签方案和超参数下的性能。研究旨在提供对常见错误的见解，并比较这两种架构在实际应用中的优劣。另外，一篇文章讨论了阅读研究论文对数据科学家的好处，强调了通过学习现有工作和了解最新进展来提高效率。
-
Eugene Yan enhances recommender systems using graph and NLP techniques
Eugene Yan's blog posts detail methods for building recommender systems that outperform baseline matrix factorization models. The approach involves using Natural Language Processing (NLP) techniques, specifically word2v…
-
Eugene Yan 分享关于推荐系统和数据角色的见解
Eugene Yan 分享了两次 DataScience SG 会议的见解，一次侧重于推荐系统，另一次侧重于数据领域的各种角色。推荐系统讲座探讨了基线方法以及新颖的图和 NLP 技术，详细介绍了从数据采集到结果比较的端到端流程。关于数据角色的小组讨论强调了逻辑思维和编程等基本技能，并强调了好奇心、毅力和谦逊对于职业成功的重要性。两次活动都强调了在快速发展的数据行业中持续自我学习的必要性。